Natural Language Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
46.67Accuracy
16
May 14, 2026
71.6Accuracy
16
Feb 26, 2026
71.1Accuracy
16
Feb 26, 2026
85.7Accuracy
16
Feb 26, 2026
45.21Accuracy
15
Feb 27, 2026
59.18Avg Test Accuracy
15
Feb 26, 2026
91.22MNLI Accuracy
14
May 28, 2026
75Accuracy
14
Apr 23, 2026
75.9Accuracy
14
Apr 23, 2026
88.1Accuracy (RTE Neg)
14
Apr 23, 2026
91.2Accuracy
14
Apr 3, 2026
51.4Accuracy
14
Feb 26, 2026
73.77Accuracy
13
Apr 28, 2026
74.22Accuracy
13
Apr 28, 2026
94.4Normalized Accuracy
13
Mar 30, 2026
96.2Normalized Accuracy
13
Mar 30, 2026
77.2Accuracy
13
Feb 27, 2026
89.3Accuracy
13
Feb 26, 2026
70.7Accuracy
13
Feb 26, 2026
84.2Accuracy
13
Feb 26, 2026
83.2Accuracy
13
Feb 26, 2026
0.803Accuracy
13
Feb 26, 2026
84.2Accuracy
13
Feb 26, 2026
70.7Accuracy
13
Feb 26, 2026
84.3Accuracy
13
Feb 26, 2026